Method and system for determining a precise value of at least one pose parameter of an ego vessel

Abstract

A method and a system for determining a precise value of at least one pose parameter of an ego vessel, on which a camera is arranged, is provided. The method includes receiving image data of an image captured by the camera, the image showing at least one solid object and at least one solid object interface between the solid object and the sky, or between the solid object and a water surface of a waterbody, on which the ego vessel sails, determining a first representation of the solid object interface, determining a coarse position of the ego vessel, determining reference data based on the coarse position of the ego vessel, determining a second representation of the solid object interface from the reference data, determining a difference between the first and second representation, and determining the precise value of the pose parameter of the ego vessel depending on the difference.

1 . A method configured to determine a precise value of at least one pose parameter of an ego vessel, on which a camera is arranged, the method comprising:
 receiving image data of an image captured by the camera, the image showing at least one solid object and at least one solid object interface between the solid object and a sky, or between the solid object and a water surface of a waterbody, on which the ego vessel sails;   determining a first representation of the solid object interface from the image data;   determining a coarse position of the ego vessel at a time at which the image is captured;   determining reference data based on the coarse position of the ego vessel, the reference data being representative of the solid object interface in a real world;   determining a second representation of the solid object interface from the reference data;   determining a difference between the first representation and the second representation; and   determining the precise value of the pose parameter of the ego vessel depending on the difference.   
     
     
         2 . The method in accordance with  claim 1 , wherein
 the determining of the difference between the first representation and the second representation comprises transferring the first representation and/or the second representation into the same coordinate system, and determining a misfit function between the first representation and the second representation within the coordinate system as the difference; and   the precise value of the pose parameter of the ego vessel is determined depending on the difference by adjusting a predetermined coarse value of the pose parameter of the ego vessel such that the difference is reduced.   
     
     
         3 . The method in accordance with  claim 2 , wherein
 the predetermined coarse value of the pose parameter is adjusted such that the misfit function is minimized.   
     
     
         4 . The method in accordance with  claim 1 , wherein
 a coarse value of at least one orientation parameter of the ego vessel is determined; and   the reference data may be determined based on the coarse value of the orientation parameter of the ego vessel.   
     
     
         5 . The method in accordance with  claim 1 ,
 wherein the first representation is representative for a pathway of the solid object interface within the image; or   wherein the second representation is representative for a pathway of the solid object interface within the real world, or   wherein the first representation is representative for a pathway of the solid object interface within the image and the second representation is representative for a pathway of the solid object interface within the real world.   
     
     
         6 . The method in accordance with  claim 1 , wherein
 when determining the second representation from the reference data, those parts of the solid object interface which were visible from the camera at the time the image was captured are determined as the first representation only.   
     
     
         7 . The method in accordance with  claim 6 , the method comprising:
 determining a positional relationship between the camera and the solid object interface from the reference data; and   determining the parts of the solid object interface which are visible from the camera depending on the determined positional relationship.   
     
     
         8 . The method in accordance with  claim 1 , wherein
 the reference data comprise 2D map data representing a 2D map of surroundings of the ego vessel.   
     
     
         9 . The method in accordance with  claim 8 , wherein
 parts of the solid object interface which are visible from the camera are determined from the 2D map data depending on the determined positional relationship between the camera and the solid object interface by ray casting.   
     
     
         10 . The method in accordance with  claim 1 , wherein
 the reference data comprise AIS data relating to at least one other vessel in the waterbody.   
     
     
         11 . The method in accordance with  claim 7 ,
 wherein the reference data comprise AIS data relating to at least one other vessel in the waterbody, the AIS data comprise a geo-location of a GPS receiver of the other vessel and an extent of the other vessel in relation to the geo-location of the GPS receiver of the other vessel;   wherein an estimated vessel-water interface between the water surface and the other vessel is estimated from the extent and the geo-location of the GPS receiver of the other vessel;   wherein the parts of the estimated vessel-water interface which are visible from the camera are determined as visible vessel-water interface depending on the estimated vessel-water interface and a position of the camera; and   wherein the visible vessel-water interface of the vessel-water interface is used as the second representation.   
     
     
         12 . The method in accordance with  claim 1 , wherein
 the reference data comprise elevation map data of a land abutting on the waterbody.   
     
     
         13 . The method in accordance with  claim 12 , wherein
 parts of the solid object interface which are visible from the camera are determined from the elevation map data by generating a textureless rendered image and by determining the second representation from the textureless rendered image.   
     
     
         14 . The method in accordance with  claim 1 ,
 wherein the image shows at least a part of a horizon between the water surface and the sky;   wherein a third representation of the horizon is determined from the image data;   wherein the reference data are representative of the horizon in the real world;   wherein a fourth representation of the horizon is determined from the reference data;   wherein a difference between the third representation and the fourth representation is determined; and   wherein the precise value of the pose parameter of the ego vessel is determined depending on the difference.   
     
     
         15 . A system configured to determine a precise value of at least one pose parameter of an ego vessel, on which a camera is arranged, the system comprising a memory configured to store image data of an image, coarse position data of the ego vessel, and/or reference data and a processing unit which is configured to carry out the method in accordance with  claim 1 .